© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9108
    Prev
    Next
    INDEX
    Explanations

    diet

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires most strongly on sequences of gerund‐form instructions (e.g. “getting enough quality sleep, drinking enough water, getting enough exercise, and the correct nutrition”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overt
    0.62
     diagnost
    0.62
     relapse
    0.62
     tolerated
    0.61
     app
    0.61
     clinically
    0.55
    诊
    0.55
     considera
    0.54
     considers
    0.54
    toler
    0.54
    POSITIVE LOGITS
    饮食
    1.46
    飲食
    1.25
     alimentação
    1.17
     diet
    1.13
    吃的
    1.13
     eating
    1.11
     eats
    1.09
    diet
    1.09
     먹
    1.08
     Eat
    1.06
    Activations Density 0.373%

    No Known Activations